convNet.pytorch

convNet.pytorch copied to clipboard

How to run the code in Colaboratory?

2

I'm trying to run main.py using colab and I executed following command in colab `!python /content/convNet.pytorch/main.py --dataset cifar10 --model resnet --model-config "{'depth': 44}" --duplicates 40 --cutout -b 64 --epochs 100...

abdulsam

Nan loss for quantization

5

I'm running the code for 8-bit quantization but found that the training loss always gets NAN while I didn't make a slight modification to the original code. Wondering why this...

syorami

why can we use apex for FP16 training? Is there any bug for L1BN2D?

guanfuchen

main.py line 287 defaults = {**train_data_defaults} - SyntaxError: invalid syntax

1

Hi, This is the output on command line: python main.py --dataset cifar10 --model resnet --model-config "{'depth': 44}" --duplicates 32 --cutout -b 64 --epochs 100 --save resnet_44_cutout_m-32-new File "main.py", line 287...

BrandonLiang

is there any plan to release the mix&match paper code

valencebond

Quantizing Mobilenet

1

I am trying to quantize mobilenet model in the same how you have implemented resnet (https://github.com/eladhoffer/convNet.pytorch). To accomplish this I added the following lines in models/mobilenet .py from .modules.quantize import...

skvenka5

Stochastic quantization: difference between code and paper

1

In the [paper](https://arxiv.org/abs/1602.02830), the stochastic quantization was done by rounding up with probability p=clip(0.5x, 0, 1), and rounding down with probability 1-p. However, in the [code](https://github.com/eladhoffer/convNet.pytorch/blob/master/models/modules/quantize.py#L67-L68) it's done by adding...

michaelklachko

Hi, cool framework! note that you add a layer of AvgPool2D with kernel=1 in the class VGG. This basically doesn't have any effect. Perhaps you meant AdaptiveAveragePool? In addition, the...

rosenfeldamir

min/max calculatation and quantize of BN layer

1

I'm curious about why you use chunk during the calculation of min and max, why not just calculate? And can't we quantize weights and bias of BN?

I-Doctor

quantization

1

If I use torch=0.2.0, I met the error: Traceback (most recent call last): File "example/mpii.py", line 352, in main(parser.parse_args()) File "example/mpii.py", line 107, in main train_loss, train_acc = train(train_loader, model,...

wm901115nwpu